Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5108
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating something is not typical or expected

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omatic
    -0.08
    bard
    -0.07
    urd
    -0.07
    âĻ¡
    -0.06
    inos
    -0.06
     ³³ ³³
    -0.06
    ÑĨем
    -0.06
    irler
    -0.06
    гов
    -0.06
    ÑĤÑı
    -0.06
    POSITIVE LOGITS
     merely
    0.14
     another
    0.13
     simply
    0.12
     mere
    0.12
    another
    0.10
    mere
    0.10
     just
    0.09
     Another
    0.09
     typical
    0.09
     like
    0.09
    Activations Density 0.030%

    No Known Activations